enhance-readme

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly shows filling username/password fields and passing credentials via CLI flags (e.g., --user/--pass and $PW fill ""), which requires embedding secrets verbatim into commands — a high-risk secret-exfiltration pattern.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (medium risk: 0.30). Outsider-authored free text can be ingested at runtime from whatever web app is provided via --url/--routes and from that page’s DOM (e.g., dismissOverlays() reads button/link text via btn.textContent) during the Playwright-based tour capture/generation.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.80). The repo's runtime scripts import and rely on npm packages (playwright and @ffmpeg-installer/ffmpeg) whose resolved registry URLs (https://registry.npmjs.org/playwright/-/playwright-1.59.1.tgz and https://registry.npmjs.org/@ffmpeg-installer/ffmpeg/-/ffmpeg-1.1.0.tgz) will be fetched/installed and can execute remote code during setup/run.